Aspects of the invention relate generally to autonomous vehicles. The features described improve the safety, use, driver experience, and performance of these vehicles by performing a behavior analysis on mobile objects in the vicinity of an autonomous vehicle. Specifically, the autonomous vehicle is
Aspects of the invention relate generally to autonomous vehicles. The features described improve the safety, use, driver experience, and performance of these vehicles by performing a behavior analysis on mobile objects in the vicinity of an autonomous vehicle. Specifically, the autonomous vehicle is capable of detecting nearby objects, such as vehicles and pedestrians, and is able to determine how the detected vehicles and pedestrians perceive their surroundings. The autonomous vehicle may then use this information to safely maneuver around all nearby objects.
대표청구항▼
1. A method for autonomous control of a vehicle, the method comprising: detecting a plurality of mobile objects external to a vehicle using one or more sensors of the vehicle;selecting, by one or more processors, a first object from the plurality of mobile objects corresponding to a second vehicle i
1. A method for autonomous control of a vehicle, the method comprising: detecting a plurality of mobile objects external to a vehicle using one or more sensors of the vehicle;selecting, by one or more processors, a first object from the plurality of mobile objects corresponding to a second vehicle in order to determine a likely behavior of the first object;determining, by the one or more processors, a position and movement of the plurality of mobile objects relative to a perspective of the first object;determining, by the one or more processors, a likely future behavior of the first object by determining how the vehicle would behave if the vehicle were placed in the position of the first object given the position and movement of the plurality of mobile objects relative to the perspective of the first object; andautonomously controlling, by the one or more processors, the vehicle relative to the first object based on the determined likely future behavior of the first object. 2. A method for autonomous navigation, the method comprising: detecting a plurality of mobile objects external to a vehicle using one or more sensors;classifying, by one or more processors, each of the plurality of mobile objects with one or more classifications;determining, by the one or more processors, a current position and movement of the plurality of mobile objects from a perspective of each mobile object of the plurality of mobile objects;determining, by the one or more processors, a likely future behavior for each mobile object by determining how the vehicle would behave if the vehicle were placed in the position of the each mobile object of the plurality of mobile objects;autonomously navigating, by the one or more processors, the vehicle based on the determined likely future behaviors of the plurality of mobile objects. 3. The method of claim 2, further comprising receiving a request to navigate between a first location and a second location, and wherein autonomously navigating the vehicle further comprises navigating the vehicle between the first location and a second location. 4. The method of claim 1, wherein the first object is traveling along a first lane of traffic, and wherein the determined likely future behavior of the first object comprises the first object changing from the first lane of traffic to a second lane of traffic. 5. The method of claim 2, wherein autonomously navigating the vehicle comprises determining a path of travel that will reduce the probability of the vehicle coming into contact with one or more of the plurality of mobile objects. 6. The method of claim 1, further comprising: selecting, by the one or more processors, a second object from the plurality of mobile objects;determining, by the one or more processors, the position and movement of the plurality of mobile objects from a perspective of the second object;accessing, by the one or more processors, behavior model data to determine a likely behavior of the second object based on the perspective of the second object and based on the determined likely future behavior of the first object; andorienting, by the one or more processors, the vehicle relative to the second object based on the determined likely future behavior of the second object. 7. The method of claim 6, further comprising: adjusting, by the one or more processors, the determined likely future behavior of the first object based on the determined likely behavior of the second object; andorienting, by the one or more processors, the vehicle relative to the first object based on an adjusted likely behavior of the first object. 8. The method of claim 1, further comprising: receiving, by the one or more processors, a request to navigate between a first location and a second location; andautonomously navigating, by the one or more processors, the vehicle between the first location and a second location, and wherein detecting the plurality of mobile objects and providing a command to orient the vehicle relative to the first object occurs while traveling along a path between the first location and the second location. 9. A system for controlling a vehicle having an autonomous operation mode, the system comprising: one or more sensors for detecting a plurality of mobile objects in a vehicle's surroundings, the one or more sensors being attached to the vehicle;a one or more memories storing control strategy data relating to operation of the vehicle in accordance with one or more control strategies; anda one or more processors in communication with the one or more sensors and the one or more memories, the one or more processors being configured to:control operation of the vehicle in accordance with a first control strategy;select a first object corresponding to a second vehicle from the plurality of mobile objects;determine a position and movement of the plurality of mobile objects with respect to a perspective of the first object;determine a likely future behavior of the first object by determining how the vehicle would behave if the vehicle were placed in the position of the first object given the determined position and movement of the plurality of mobile objects with respect to the perspective of the first object; andcontrol operation of the vehicle in accordance with a second control strategy, wherein the second control strategy is based on the determined likely future behavior of the first object. 10. The method of claim 2, further comprising adjusting the determined likely future behavior of each mobile object of the plurality of mobile objects based on the determined likely behavior of all other mobile objects, and wherein autonomously navigating the vehicle is based on the adjusted likely future behavior of the first object. 11. The method of claim 2, wherein the classifications comprise an automobile, a pedestrian, and a bicycle. 12. The system of claim 9, wherein the first object is traveling along a first lane of traffic, and wherein the determined likely future behavior of the first object comprises the first object changing from the first lane of traffic to a second lane of traffic. 13. The system of claim 12, wherein the second control strategy comprises having the vehicle travel in a lane of traffic other than the second lane of traffic. 14. The system of claim 3, wherein the processor is operable to: select a second object from the plurality of mobile objects;determine the position and movement of the plurality of mobile objects from a perspective of the second object;access behavior model data to determine a likely future behavior of the second object based on the determined position and movement of the plurality of mobile objects and based on the determined likely future behavior of the first object;control operation of the vehicle in accordance with a third control strategy, wherein the third control strategy is based on the determined likely future behavior of the second object. 15. The system of claim 14, wherein the processor is operable to adjust the likely future behavior of the first object based on the determined likely behavior of the second object, and wherein the third control strategy is based on an adjusted likely future behavior of the first object. 16. The system of claim 9, wherein the processor is operable to: receive a request to navigate between a first location and a second location; andautonomously navigating the vehicle between the first location and a second location, and wherein providing a command to orient the vehicle relative to the first object occurs while traveling along a path between the first location and the second location.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (35)
Bergholz Ralf,DEX ; Timm Klaus,DEX ; Weisser Hubert,DEX, Autonomous vehicle arrangement and method for controlling an autonomous vehicle.
Trepagnier, Paul Gerard; Nagel, Jorge Emilio; Dooner, Matthew Taylor; Dewenter, Michael Thomas; Traft, Neil Michael; Drakunov, Sergey; Kinney, Powell; Lee, Aaron, Control and systems for autonomously driven vehicles.
Trepagnier, Paul Gerard; Nagel, Jorge Emilio; Dooner, Matthew Taylor; Dewenter, Michael Thomas; Traft, Neil Michael; Drakunov, Sergey; Kinney, Powell; Lee, Aaron, Control and systems for autonomously driven vehicles.
Stortz, Christiane; Winter, Klaus; Lehre, Klaus; Marchthaler, Reiner, Method and device for identifying the state of a system for effecting the automatic longitudinal and/or lateral control of a motor vehicle.
Preston, Dan; Preston, Joseph David; Blum, Rick Scott; Manos, Thomas August; Schofield, Kenneth, System and method for the configuration of an automotive vehicle with modeled sensors.
Thalanany, Sebastian; Saxena, Narothum; Irizarry, Michael S., Configuring traffic control device switch timing intervals using mobile wireless device-provided traffic information.
Ferguson, David Ian Franklin; Wendel, Andreas; Xu, Zhinan; Silver, David Harrison; Luders, Brandon Douglas, Determining drivability of objects for autonomous vehicles.
Chan, Alistair K.; Cheatham, III, Jesse R.; Chin, Hon Wah; Duncan, William David; Hyde, Roderick A.; Tuckerman, David B.; Weaver, Thomas Allan, Driver training in an autonomous vehicle.
Schmüdderich, Jens; Richter, Andreas, Method and system for using global scene context for adaptive prediction and corresponding program, and vehicle equipped with such system.
Jones, Matt; Bontrager, Peter; Paszkowicz, Sebastian; Wheller, Paul, System and method for configuring autonomous vehicle responses based on a driver profile.
Fields, Brian Mark; Cielocha, Steven C.; Alt, Jacob J.; Uphoff, Laura Anne; Chan, Leo Nelson; Wazeer, Mohamed A.; Gaudin, Kristopher Keith; Davis, Justin; Baumann, Nathan W.; Roll, Giles, Vehicular warnings based upon pedestrian or cyclist presence.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.